Low-light raw image denoising plays a crucial role in mobile photography, and learning-based methods have become the mainstream approach. Training the learning-based methods with synthetic data emerges as an efficient and practical alternative to paired real data. However, the quality of synthetic data is inherently limited by the low accuracy of the noise model, which decreases the performance of low-light raw image denoising. In this paper, we develop a novel framework for accurate noise modeling that learns a physics-guided noise neural proxy (PNNP) from dark frames. PNNP integrates three efficient techniques: physics-guided noise decoupling (PND), physics-guided proxy model (PPM), and differentiable distribution-oriented loss (DDL). The PND decouples the dark frame into different components and handles different levels of noise in a flexible manner, which reduces the complexity of the noise neural proxy. The PPM incorporates physical priors to effectively constrain the generated noise, which promotes the accuracy of the noise neural proxy. The DDL provides explicit and reliable supervision for noise modeling, which promotes the precision of the noise neural proxy. Extensive experiments on public low-light raw image denoising datasets and real low-light imaging scenarios demonstrate the superior performance of our PNNP framework.
相關內容
Focus stacking is widely used in micro, macro, and landscape photography to reconstruct all-in-focus images from multiple frames obtained with focus bracketing, that is, with shallow depth of field and different focus planes. Existing deep learning approaches to the underlying multi-focus image fusion problem have limited applicability to real-world imagery since they are designed for very short image sequences (two to four images), and are typically trained on small, low-resolution datasets either acquired by light-field cameras or generated synthetically. We introduce a new dataset consisting of 94 high-resolution bursts of raw images with focus bracketing, with pseudo ground truth computed from the data using state-of-the-art commercial software. This dataset is used to train the first deep learning algorithm for focus stacking capable of handling bursts of sufficient length for real-world applications. Qualitative experiments demonstrate that it is on par with existing commercial solutions in the long-burst, realistic regime while being significantly more tolerant to noise. The code and dataset are available at //github.com/araujoalexandre/FocusStackingDataset.
State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image capture. The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a text-to-image diffusion model with the particular lens geometry used in image rendering. Our method is based on a per-pixel coordinate conditioning method, enabling the control over the rendering geometry. Notably, we demonstrate the manipulation of curvature properties, achieving diverse visual effects, such as fish-eye, panoramic views, and spherical texturing using a single diffusion model.
Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders with significant memory and latency overhead which pose challenges for deployment on mobile devices. In this work, we introduce MobileCLIP -- a new family of efficient image-text models optimized for runtime performance along with a novel and efficient training approach, namely multi-modal reinforced training. The proposed training approach leverages knowledge transfer from an image captioning model and an ensemble of strong CLIP encoders to improve the accuracy of efficient models. Our approach avoids train-time compute overhead by storing the additional knowledge in a reinforced dataset. MobileCLIP sets a new state-of-the-art latency-accuracy tradeoff for zero-shot classification and retrieval tasks on several datasets. Our MobileCLIP-S2 variant is 2.3$\times$ faster while more accurate compared to previous best CLIP model based on ViT-B/16. We further demonstrate the effectiveness of our multi-modal reinforced training by training a CLIP model based on ViT-B/16 image backbone and achieving +2.9% average performance improvement on 38 evaluation benchmarks compared to the previous best. Moreover, we show that the proposed approach achieves 10$\times$-1000$\times$ improved learning efficiency when compared with non-reinforced CLIP training.
Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images.
Inverse rendering of outdoor scenes from unconstrained image collections is a challenging task, particularly illumination/albedo ambiguities and occlusion of the illumination environment (shadowing) caused by geometry. However, there are many cues in an image that can aid in the disentanglement of geometry, albedo and shadows. We exploit the fact that any sky pixel provides a direct measurement of distant lighting in the corresponding direction and, via a neural illumination prior, a statistical cue as to the remaining illumination environment. We also introduce a novel `outside-in' method for computing differentiable sky visibility based on a neural directional distance function. This is efficient and can be trained in parallel with the neural scene representation, allowing gradients from appearance loss to flow from shadows to influence estimation of illumination and geometry. Our method estimates high-quality albedo, geometry, illumination and sky visibility, achieving state-of-the-art results on the NeRF-OSR relighting benchmark. Our code and models can be found //github.com/JADGardner/neusky
Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion guidance remains largely unexplored. We propose Dream-in-4D, which features a novel two-stage approach for text-to-4D synthesis, leveraging (1) 3D and 2D diffusion guidance to effectively learn a high-quality static 3D asset in the first stage; (2) a deformable neural radiance field that explicitly disentangles the learned static asset from its deformation, preserving quality during motion learning; and (3) a multi-resolution feature grid for the deformation field with a displacement total variation loss to effectively learn motion with video diffusion guidance in the second stage. Through a user preference study, we demonstrate that our approach significantly advances image and motion quality, 3D consistency and text fidelity for text-to-4D generation compared to baseline approaches. Thanks to its motion-disentangled representation, Dream-in-4D can also be easily adapted for controllable generation where appearance is defined by one or multiple images, without the need to modify the motion learning stage. Thus, our method offers, for the first time, a unified approach for text-to-4D, image-to-4D and personalized 4D generation tasks.
Learning based image quality assessment (IQA) models have obtained impressive performance with the help of reliable subjective quality labels, where mean opinion score (MOS) is the most popular choice. However, in view of the subjective bias of individual annotators, the labor-abundant MOS (LA-MOS) typically requires a large collection of opinion scores from multiple annotators for each image, which significantly increases the learning cost. In this paper, we aim to learn robust IQA models from low-cost MOS (LC-MOS), which only requires very few opinion scores or even a single opinion score for each image. More specifically, we consider the LC-MOS as the noisy observation of LA-MOS and enforce the IQA model learned from LC-MOS to approach the unbiased estimation of LA-MOS. In this way, we represent the subjective bias between LC-MOS and LA-MOS, and the model bias between IQA predictions learned from LC-MOS and LA-MOS (i.e., dual-bias) as two latent variables with unknown parameters. By means of the expectation-maximization based alternating optimization, we can jointly estimate the parameters of the dual-bias, which suppresses the misleading of LC-MOS via a gated dual-bias calibration (GDBC) module. To the best of our knowledge, this is the first exploration of robust IQA model learning from noisy low-cost labels. Theoretical analysis and extensive experiments on four popular IQA datasets show that the proposed method is robust toward different bias rates and annotation numbers and significantly outperforms the other learning based IQA models when only LC-MOS is available. Furthermore, we also achieve comparable performance with respect to the other models learned with LA-MOS.
Text-image composed retrieval aims to retrieve the target image through the composed query, which is specified in the form of an image plus some text that describes desired modifications to the input image. It has recently attracted attention due to its ability to leverage both information-rich images and concise language to precisely express the requirements for target images. However, the robustness of these approaches against real-world corruptions or further text understanding has never been studied. In this paper, we perform the first robustness study and establish three new diversified benchmarks for systematic analysis of text-image composed retrieval against natural corruptions in both vision and text and further probe textural understanding. For natural corruption analysis, we introduce two new large-scale benchmark datasets, CIRR-C and FashionIQ-C for testing in open domain and fashion domain respectively, both of which apply 15 visual corruptions and 7 textural corruptions. For textural understanding analysis, we introduce a new diagnostic dataset CIRR-D by expanding the original raw data with synthetic data, which contains modified text to better probe textual understanding ability including numerical variation, attribute variation, object removal, background variation, and fine-grained evaluation. The code and benchmark datasets are available at //github.com/SunTongtongtong/Benchmark-Robustness-Text-Image-Compose-Retrieval.
Score-based diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. Recently, a number of theoretical works \citep{chen2022, Chen2022ImprovedAO, Chenetal23flowode, benton2023linear} have shown that diffusion models can efficiently sample, assuming $L^2$-accurate score estimates. The score-matching objective naturally approximates the true score in $L^2$, but the sample complexity of existing bounds depends \emph{polynomially} on the data radius and desired Wasserstein accuracy. By contrast, the time complexity of sampling is only logarithmic in these parameters. We show that estimating the score in $L^2$ \emph{requires} this polynomial dependence, but that a number of samples that scales polylogarithmically in the Wasserstein accuracy actually do suffice for sampling. We show that with a polylogarithmic number of samples, the ERM of the score-matching objective is $L^2$ accurate on all but a probability $\delta$ fraction of the true distribution, and that this weaker guarantee is sufficient for efficient sampling.
The low resolution of objects of interest in aerial images makes pedestrian detection and action detection extremely challenging tasks. Furthermore, using deep convolutional neural networks to process large images can be demanding in terms of computational requirements. In order to alleviate these challenges, we propose a two-step, yes and no question answering framework to find specific individuals doing one or multiple specific actions in aerial images. First, a deep object detector, Single Shot Multibox Detector (SSD), is used to generate object proposals from small aerial images. Second, another deep network, is used to learn a latent common sub-space which associates the high resolution aerial imagery and the pedestrian action labels that are provided by the human-based sources
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191